Self-Supervised AI Discovery of Histomorphological Phenotypes from Routine Mesothelioma Biopsies
Year: 2026
Type: preprint
Study design: Observational Study
Abstract: Accurate subtype diagnosis is essential for guiding therapy and predicting patient outcome in malignant mesothelioma. Most computational pathology models are trained on large tissue images from resection specimens, which maximises information for training but limits model relevance in real-world diagnostic settings where small biopsies are the most usual tissue source. In this work, we assembled a large multicentre cohort of mesothelioma biopsy slides. We used a self-supervised learning model to evaluate the associations of biopsy-driven morphology patterns with histological subtype, molecular markers, and survival. The discovered histomorphology patterns captured a continuum of tissue phenotypes spanning epithelioid and sarcomatoid malignancy and non-tumour morphologies. Furthermore, patient-level HPC representations performed excellently in distinguishing epithelioid from non-epithelioid mesothelioma (AUC = 0.94) and demonstrated prediction of immunohistochemistry (IHC) markers. Additionally, HPC-derived features alone achieved performance comparable to established clinical and molecular variables (C-index = 0.65), while integration of HPCs with clinical and marker information improved performance to a C-index of 0.69. Several HPCs were significantly associated with either favourable or adverse prognosis and reflected both clinically known and biologically plausible patterns. In conclusion, self-supervised learning can discover interpretable histomorphological phenotypes directly from routine mesothelioma small biopsies without further training. These AI-derived phenotypes capture clinically and biologically relevant information, linking tissue architecture to molecular characteristics, histological subtypes, and patient outcomes. The proposed framework provides a thorough evaluation of real-world biopsy data using a pre-trained model, without the need for computationally intensive retraining, and addresses the question of whether SSL-based AI can be deployed out of the box in clinical settings.
Source: Research Square
Language: English
Topic: AI in cancer detection
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7202209959